Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/angadhn/botference/agent-basegit clone --depth 1 https://github.com/angadhn/botferenceWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00558 |
| Opus 5 | $0.00000 | $0.00279 |
| Sonnet 5 | $0.00000 | $0.00112 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
agent-base scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Base — Shared Protocol
All agents inherit these rules. Agent-specific prompts override when they conflict.
Path Resolution
botference may run as an engine on a separate project repo. Two roots exist:
- BOTFERENCE_HOME (framework): contains
specs/,templates/,scripts/,tools/, and built-in.claude/agents/ - Working directory (project): contains
work/(thread state),build/(generated outputs),sections/,figures/,corpus/,references/,papers/ - Agent files resolve workspace-first:
.claude/agents/{name}.mdis checked in the project directory before BOTFERENCE_HOME. Custom agents in the workspace override built-in agents of the same name.
When a "Path Context" section is present at the top of this prompt, use its BOTFERENCE_HOME path to prefix framework file reads (e.g., specs/writing-style.md → $BOTFERENCE_HOME/specs/writing-style.md). Project files are always relative to the working directory.
When no Path Context is present, BOTFERENCE_HOME equals the working directory — all paths resolve as-is.
Budget and Yield
- Before each major step, read
$BOTFERENCE_RUN/budget-info(BOTFERENCE_RUN defaults to./run). Follow its recommendation: PROCEED, CAUTION (finish current step only), or YIELD (save state and exit). - Before each major step, check
$BOTFERENCE_RUN/yield. If it exists, updatecheckpoint.mdand exit immediately.
Incremental Commit
After each major step, commit all modified output files immediately (git add <outputs> && git commit). This caps work loss to one step if the process dies.
Checkpoint Discipline
- Read
checkpoint.mdfirst — it determines your task and mode. - Write
checkpoint.mdlast — update Knowledge State and set Next Task for the next agent. - Before exiting (normal or yield): always commit your critical deliverable +
checkpoint.md.
Parallel Execution
When running as part of a parallel phase, the environment variable PARALLEL_TASK_IDX is set to a unique integer identifying this agent's task slot. If PARALLEL_TASK_IDX is set, namespace output files with it to avoid collisions with other parallel agents writing to the same canonical paths.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 43 lines · 0 tokens per session scan A a4e857057e3a
agent-base is an agent published in the GitHub repository angadhn/botference (19 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 558 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.